Department of Statistics Unitmark
Dietrich College of Humanities and Social Sciences

Search form

Kathryn Roeder named Carnegie Mellon University Professor

May 18, 2020, 1:20PM

"University Professors are distinguished by international recognition and for their contributions to education, artistic creativity and/or research," said Provost Jim Garrett. "Each University Professor exemplifies a high level of professional achievement and an exceptional commitment to academic excellence at our university." Garrett said the professors were nominated and recommended by academic leaders and faculty who have achieved the designation of University Professor.

Kathryn holds appointments in the Department of Statistics & Data Science and the Computational Biology Department. She also served as the university's vice provost for faculty from July 2015 through June 2019.

She started her research career in biology but was soon drawn to statistics. Her first major data project was in DNA forensics, helping to solidify the credibility of this form of evidence in the judicial system. As her scientific career advanced, she transitioned to developing statistical and machine learning tools for finding associations or patterns in data. She focuses on high-dimensional inference problems with applications such as analyzing variation in the...

Read more

Outstanding TA Awards

May 15, 2020, 9:46AM

Undergrad program:
Outstanding TAs: Sammie Liang, Ananya Vasudev, Anastasia Wass
TA of the Year: Elsie Goren

Master’s in Statistical Practice:
Outstanding TAs: Esther Kaydanovsky, Alex Messam, Julia Stelman
TA of the Year: Sophia Hecht

PhD program TAs of the Year:
Fall 2019: Nic Dalmasso, Shamindra Shrotriya
Spring 2020: Ciaran Evans, Kevin Lin

Research Showcase Winners

May 15, 2020, 9:25AM

And the winners were:

Graphics:
1st place: The Avocado-Apocalypse by Hannah Douglas, Sweta Kotha, Jonathan Wang, Stuart Wilkins
2nd place: Global Terrorism by Yurong Li, Xinyu Ma, Xinzhe Qi, Jingyan Xu
3rd place: Did the Orlando Nightclub Shooting Affect the Florida State Patrol’s Stopping Behavior? A Pre-Causal Analysis by Carlo Duffy, Ryan Labriola, Yedin Liu

Early Research:
Classifying Kepler Objects of Interest by Andrew Furlong, James Lederman, Lajja Pancholy, Ananya Vasudev
Advised by Peter Freeman

Advanced Research:
Text Analysis of U.S. Congressional Records by Adam Behnke, James Mahler, Parvathi Meyyappan, Youna Song
Advised by Dani Nedal and Zach Branson

DSI Corporate Capstone:
1st place: Natural Language Processing for Receipt Classification by Richard Chun, Andrew Gu, Malik Khan, Taewan Kim, Eva Zhong
Collaboration with The NPD Group, advised by Yufei Yi and Peter Freeman

Hon Men: Predicting Customer Segmentation from Transactional Data by Rahul Ahuja, Hanyue Chai, Aayush Jain, Chenxiang Zhang
Collaboration with...

Read more

Award Winning JSM Student Papers

February 4, 2020, 11:30AM

Four Department of Statistics & Data Science graduate students have been named winners in the Joint Statistical Meetings student paper competitions.
The meetings will be held August 1-6 in Philadelphia, PA.

Kwangho Kim - Winner in the Nonparametric Statistics section for his paper "Incremental Intervention Effects in Studies with Many Timepoints, Repeated Outcomes, and Dropout."

Collin Politsch - Winner in the Astrostatistics paper competition for his paper "Trend Filtering: A Modern Statistical Tool for Time-Domain Astronomy and Astronomical Spectroscopy." (Also accepted for publication in Monthly Notices of the Royal Astronomical Society.)

Matteo Bonvini - His paper "Sensitivity Analysis via the Proportion of Unmeasured Confounding," won a Young Investigator Award in the Statistics in Epidemiology section.

Ilmun Kim - Winner in the Statistical Learning and Data Science paper competition for "Classification Accuracy as a Proxy for Two-Sample Testing."

Congratulations to all!

Kathryn Roeder selected to give 2020 RA Fisher Award Lecture

January 17, 2020, 12:21PM

Kathryn Roeder has been selected to give the 2020 RA Fisher Award Lecture at
the joint statistics meetings this summer in Philadelphia (Wednesday, Aug 5).

The R.A. Fisher Lectureship was established in 1963 by COPSS (the
Committee of Presidents of Statistics Societies) to honor both the
contributions of Sir Ronald Aylmer Fisher and the work of a present–day
statistician for their advancement of statistical theory and
applications. The Fisher Lectureship is a very high recognition of
meritorious achievement and scholarship in statistical science and
recognizes highly significant impact of statistical methods on scientific
investigations. The award winner will receive a plaque and a cash
honorarium, and deliver the Fisher Lecture at the Joint Statistical Meetings

Past winners include Steve Fienberg and Rob Kass. For a full list of
past recipients see: https://en.wikipedia.org/wiki/R._A._Fisher_Lectureship

New England Symposium on Statistics in Sports

October 4, 2019, 12:16PM

NESSIS, the New England Symposium on Statistics in Sports was held on October 28 at Harvard University. S&DS students Riccardo Fogliato, Natalia Lombardi de Oliveira and Ron Yurko won the Best Student Poster prize for their work on "TRAP: A Predictive Framework for Trail Running Assessment of Performance."

Another CMU featured project was "Going Deep Models for Continuous-Time Within-Play Valuation of Game Outcomes in American Football with Tracking Data." Ron Yurko was the primary author/speaker; work by Francesca Matano, Lee Richardson, Sam Ventura, Taylor Pospisil and Ann Lee, along with University of Pittsburgh's Nick Granered and Kostas Pelechrinis, was also incorporated.

Statistics Undergrad News

September 9, 2019, 2:52PM

Corey Emery (StatML, HCI) and Shlok Goyal (Econ, StatML, CS minor) have been selected as two of the eight 2019-2020 Dietrich Andrew Carnegie Society Scholars! It’s a very prestigious undergrad-level award, and only around 40 students are selected each year from across the campus. You can learn more about the ACS and the ACS Scholars here.

Hannah Douglas (StatNeuro, Sr), the current president of the Japanese Student Association, explained Suikawari to the Pittsburgh Post Gazette. It involves watermelons, blindfolds, and swords (?). Watch the video.

S&DS and Data Science Club Welcomed Hadley Wickham

September 4, 2019, 10:05AM

His work includes packages for data science (the tidy verse: including ggplot2, dplyr, tidyr, purrr, and readr) and principled software development (roxygen2, testthat, devtools, pkgdown). He is also a writer, educator, and speaker promoting the use of R for data science. Learn more on his website, http://hadley.nz.

"For a long time, I've wondered exactly what it is that I do. It’s obvious that I don't develop new mathematical theory, and while I do a lot of software development, it feels like software is only part of what I produce. I spend a lot of time thinking about how data analysis should "feel" and how the various pieces should fit together in order to provide a cohesive experience. Recently, thanks to prompting from Hilary Parker, I've realised that perhaps what I do most is design: the study of the human-made world, and development of practical, empathic, and useful tools. In this talk, I'll discuss the importance of design in my work, how it has shaped my career, and some of my greatest successes and failures."

The Statistics & Data Science Department and the Data Science Club thanks everyone for...

Read more

Abby Flynt (PhD 2012) awarded Chikio Hayashi Award

June 26, 2019, 9:58AM

Abby received her PhD from the Department of Statistics in 2012 and is currently at Bucknell University Department of Mathematics. She is the incoming President of the North America Classification Society.

Joel Greenhouse co-authors study on Netflix series "13 Reasons Why"

May 8, 2019, 10:14AM

"13 Reasons Why" tells the story of a young girl who kills herself and leaves behind a series of 13 tapes detailing the reasons why she chose to end her life. "Youth may be particularly susceptible to suicide contagion, which can be fostered by stories that sensationalize or promote simplistic explanations of suicidal behavior, glorify or romanticize the decedent, present suicide as a means of accomplishing a goal or offer potential prescriptions of how-to die by suicide," said Jeff Bridge, from Ohio State University.

The authors used interrupted time series and forecasting models to analyze monthly rates of suicide between Jan. 1, 2013 and Dec. 31, 2017 — the time period before and after the release of "13 Reasons Why." "We adjusted for potential effects of seasonality and underlying trends on suicide rates and estimated that the series' release was associated with approximately 195 additional suicide deaths in 2017 for 10- to 17-year-olds," said Joel Greenhouse, professor of statistics in CMU's Dietrich College of Humanities and Social Sciences, the second author on the study. "Interestingly, there was no significant association between the...

Read more

Pages